1 citations · 1 across the 5 of their papers we have counts for
7 papers
Language Model Fingerprinting Requires Rethinking Watermark Teachers
Jeongyeon Hwang, Anshul Nasery, Sewoong Oh +1
LLM fingerprinting via watermark distillation embeds a statistical watermark signal into model weights, enabling model owners to identify their models behind black-box APIs. Revisi…
Retrospective Distillation Attribution via Normalized Response Similarity
Minwoo Jang, Jaechang Kim, Minhyeon Oh +2
Model distillation transfers capabilities through supervised fine-tuning (SFT) on teacher responses, often collected from commercial APIs, raising questions of model provenance. Ex…
LLM Watermark Evasion via Bias Inversion
Jeongyeon Hwang, Sangdon Park, Jungseul Ok
Watermarking offers a promising solution for detecting LLM-generated content, yet its robustness under realistic query-free (black-box) evasion remains an open challenge. Existing…
Efficient Latent Semantic Clustering for Scaling Test-Time Computation of LLMs
Sungjae Lee, Hoyoung Kim, Jeongyeon Hwang +2
Scaling test-time computation--generating and analyzing multiple or sequential outputs for a single input--has become a promising strategy for improving the reliability and quality…
Retrieval-Augmented Generation with Estimation of Source Reliability
Jeongyeon Hwang, Junyoung Park, Hyejin Park +3
Retrieval-Augmented Generation (RAG) is an effective approach to enhance the factual accuracy of large language models (LLMs) by retrieving information from external databases, whi…
MedBN: Robust Test-Time Adaptation against Malicious Test Samples
Hyejin Park, Jeongyeon Hwang, Sunung Mun +2
Test-time adaptation (TTA) has emerged as a promising solution to address performance decay due to unforeseen distribution shifts between training and test data. While recent TTA m…
Addressing Feature Imbalance in Sound Source Separation
Jaechang Kim, Jeongyeon Hwang, Soheun Yi +2
Neural networks often suffer from a feature preference problem, where they tend to overly rely on specific features to solve a task while disregarding other features, even if those…